Cognigy

Cognigy.AI Docs

COGNIGY.AI is the Conversational AI Platform focused on the needs of large enterprises to develop, deploy and run Conversational AI’s on any conversational channel.

Given the arising need of voice interfaces as the most natural way of communicating with brands, Cognigy was founded in 2016 by Sascha Poggemann and Phil Heltewig. Our mission: to enable all devices and applications to intelligently communicate with their users via naturally spoken or written dialogue.

Get Started

Endpoints

Description

In Cognigy.AI, Endpoints connect Channels (e.g. Webchat, Facebook, Teams or Twilio) to a Cognigy Flow.

The Endpoint receives the message from the channel and formats it in a way that Cognigy.AI can understand it. After NLU and the Flow have been processed, Flow Outputs go back to the Endpoint, which returns a correctly formatted message into the Channel.

The following channels are available:

Creation

You can create an Endpoint within a project by clicking the button in the resource list with the plus sign (see Figure 2).

Figure 2: Button for creating an Endpoint

Configuration

The configuration page of an Endpoint has at least two sections regardless of the selected type:

  • General Settings
  • Data Management

You can get detailed descriptions about the General Settings and Data Management by visiting the following pages:

Accessing the Channel in a Flow

If you want to know which channel the user is connecting through, then you can access ci.channel in your Flow. The value of ci.channel will depend on the channel the user is currently using and can be one of the following:

Channel Name

Channel Value (ci.channel)

Webchat

For the Webchat, the channel can either be:

  • admin-webchat: This is the value when using the demo webchat page

  • webchat-client: This is the default value when embedding the webchat on a page

When embedding the Webchat on a website, you can override the default value of "webchat-client" with any value you choose, to e.g. differentiate between webchats on different websites.

Alexa

alexa

Dialogflow

dialogflow

Google Actions

google

Intercom

intercom

LINE Messenger

line

Facebook Messenger

facebook

Microsoft Bot Framework

microsoftBotFramework

Microsoft Teams

microsoftTeams

Slack

slack

Smooch

smooch

Twilio

twilio

TwilioSMS

twilio-sms

Userlike

userlike

Webhook

webhook

Socket

socket

REST

rest

Webchat LEGACY

webchat

Interaction Panel

adminconsole

Updated 5 months ago



Endpoints


Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.